Prediction of Contact Maps Using Support Vector Machines

Contact map prediction is of great interest for its application in fold recognition and protein 3D structure determination. In this paper we present a contact-map prediction algorithm that employs Support Vector Machines as the machine learning tool and incorporates various features such as sequence profiles and their conservation, correlated mutation analysis based on various amino acid physicochemical properties, and secondary structure. In addition, we evaluated the effectiveness of the different features on contact map prediction for different fold classes. On average, our predictor achieved a prediction accuracy of 0.2238 with

• Type: Conference
• Year: 2003
• Where: BIBE
• Authors: Ying Zhao, George Karypis
• Keywords: Amino Acid Physicochemical, BIBE 2003, Bioinformatics, Contact Map Prediction, Contact-map Prediction Algorithm